lib
claudecodexCLI wrapper skills: Slack, Jira, GitHub, TestRail, vault operations, log analysis, and file utilities
18 skills · hooks
Build and maintain a verified Figma component library from real code. Resumable, schema-validated extraction and planning; Figma is one renderer.
Plugin design-lab from marketplace local in cosmicdreams/claude-plugins. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
captureMeasure and photograph inventoried components on a running site at documented breakpoints. Produces source-fidelity measurements and element-scoped screenshots for Figma components and cards. Not for discovering components (design-lab:inventory) or counting usage (design-lab:usage).
detectDetect prior design-system work and the independent component, token, and usage sources in a repository. Run before extraction; not for extracting components (design-lab:inventory) or building Figma (design-lab:figma-component).
evaluateScore a finished design-lab run and produce a presentable, self-contained HTML report — what was built, how faithful it is to the live site, what it cost, and how repeatable it is — plus a schema-validated scorecard and the fixed completion message. design-lab:run calls it as its last step; also use
figma-buildBuild an earlier design-lab run's capture and plan into a new, empty Figma file, as a new run with its own pane, verification and report: minutes, where a fresh capture takes hours. Use to rebuild a library into a fresh file, after a design-lab update or to show the build. Not for capturing or plann
figma-componentBuild, rebuild or diagnose ONE component in the Figma library: its responsive master, its documentation block, its live captures and its visual comparison. Invoke as `design-lab:figma-component` with a component id. Not for foundations (design-lab:figma-foundation), the Getting Started page (design-
figma-foundationExplain, rebuild or diagnose the library's pages, variables and Foundations pages (Color, Typography, Spacing & Layout, Elevation & Shape, Brand Voice & Language). Run as part of design-lab:run; use alone to refresh foundations after tokens or published copy change. Not for components (design-lab:fi
figma-indexRebuild the Getting Started page — coverage, how the file is organised, what each component block shows, the linked index, known gaps, changelog and provenance — from the recorded build. Run after any component is built or rebuilt. Not for building components (design-lab:figma-component) or the fina
initSet design-lab up for the person and this machine, once: where runs live, their name for reports, the shared Playwright and its browser, the pinned Node dependencies, the Figma runner, and the Claude Code settings that would otherwise make runs ask for approval. Run it the first time design-lab is u
inventoryExtract source components, fields, options, slots, relationships, and source defects into a validated components.json. Run after detection; not for deciding the Figma representation (design-lab:plan).
planConvert validated components.json into a durable, reviewable Figma build plan with properties, variant arithmetic, flags, and explicit refusals. Run before any Figma mutation. Not for extraction (design-lab:inventory).
runBuild or refresh a complete Figma component library from a real codebase, beginning with source discovery and ending with whole-file verification. Use for end-to-end library work. Not for a single phase on its own — detection (design-lab:detect), extraction (design-lab:inventory), one component (des
tokensExtract source-backed color, spacing, typography, and other design tokens into validated tokens.json with breakpoint values, provenance, and real code identifiers. Run before the Figma foundation; not for component extraction (design-lab:inventory).
usageMeasure where source components are actually placed and attach verified examples, placement counts, structural references, and usage tiers to components.json. Run after inventory; not for visual capture (design-lab:capture).
verifyVerify an entire built Figma library against the versioned design-lab standard, fixing every blocker or major finding. Run before handoff; not for extraction (design-lab:inventory) or component construction (design-lab:figma-component).
/design-lab:recapShow a finished design-lab run's recap: the Figma file, coverage, accuracy, time, tokens and the developer audit
/design-lab:watchShow where the design-lab run is, in a pane that stays open until it is done
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard_runner_token.ts"
CLI wrapper skills: Slack, Jira, GitHub, TestRail, vault operations, log analysis, and file utilities
18 skills · hooks
Drupal-specific development skills and agents (DDEV, Analysis, Validation, Scaffolding)
13 skills · 1 agent · hooks
Passive knowledge capture pipeline — Karpathy-derived LLM Wiki with Monitor-driven multi-domain ingest. Feeds land in raw/, agents compile them into a cross-linked Obsidian wiki, memory evolves via confidence decay and graph-aware consolidation.
12 skills · 2 agents
Knowledge-work verbs as standalone compositional primitives: frame, gather, understand, synthesize, interrogate, experiment, teach. NotebookLM + Workflow fan-out; preflight-first input contracts; no orchestrator
8 skills · 3 agents · hooks
Process automation skills: prioritize, scout, knowledge-check, deploy checklist, Obsidian maintenance, and personal productivity
12 skills
Plugin, agent, and skill management tooling: bump-version, scaffold, new-agent, optimize-agents, update-plugins, create-worktree
9 skills · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.